BriefGPT.xyz
Jun, 2022
基于多尺度图嵌入的图核
Graph Kernels Based on Multi-scale Graph Embeddings
HTML
PDF
Wei Ye, Hao Tian, Qijun Chen
TL;DR
本文提出了一种新型图核心方法,称为多尺度路径结构图核心方法(MPG),它考虑了子结构的分布和不同尺度的图结构,并使用Wasserstein距离计算相似度,实验结果表明其性能超越了现有方法。
Abstract
graph kernels
are conventional methods for computing graph similarities. However, most of the R-convolution
graph kernels
face two challenges: 1) They cannot compare graphs at multiple different scales, and 2) th
→